© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21051
    Prev
    Next
    INDEX
    Explanations

    people's names and roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     essentielle
    -1.24
     universelle
    -1.23
     юби
    -1.20
    conducted
    -1.17
     ideen
    -1.17
     primul
    -1.16
    olving
    -1.15
     NEWSLETTER
    -1.13
     député
    -1.13
     fiecare
    -1.12
    POSITIVE LOGITS
     that
    2.03
     to
    1.47
     inasmuch
    1.33
     because
    1.27
    公園
    1.23
     would
    1.22
     until
    1.18
     without
    1.16
     what
    1.13
     which
    1.10
    Activations Density 0.183%

    No Known Activations